O.V. Drozd1

1 Siberian Federal University (Krasnoyarsk, Russia)

1 odrozd@sfu-kras.ru

In the development of unmanned aerial vehicles (UAV), ground testing of proposed technical solutions is an important part to ensure that the test object meets the functional requirements. Currently, approaches to debugging and testing of UAV systems are being actively developed using modular testing tools for on-board UAV systems based on Hardware-in-the-Loop simulation. The key role is played by measuring systems (stands) with full or partial simulation of the on-board control systems functioning.

The aim of this work is to provide autonomous testing of unmanned aerial vehicles by using the Hardware-in-the-Loop technology of the navigation system. In this case, the problem of providing UAV autonomous group navigation by visual reference points is considered, including in a complex interference environment of real operating conditions. To achieve this goal, the Hardware-in-the-Loop simulation system of the unmanned aerial vehicle autonomous navigation was developed, which ensures the development and testing of algorithms for UAV group navigation in the absence of navigation signals from global positioning systems (GPS, GLONASS).

The technical implementation and simulation results of the proposed system for semi-field simulation of autonomous navigation are considered in detail. The proposed Hardware-in-the-Loop simulation system includes: the library of reference point coordinates, the module for forming and correcting the target UAV flight trajectory, the neural network model of UAV group autonomous navigation, the module for evaluation the navigation task quality indicators, the UAV spatial dynamics model, the external influences model (atmospheric parameters and random air fluctuations). To ensure group autonomous navigation, a combination of convolutional (CNN) and recurrent (RNN) neural networks with long-short-term memory (LSTM) blocks is used. The process of conducting autonomous tests using the proposed system involves the formation of initial conditions and flight scenarios, training the autonomous navigation neural network, modeling the flight route and the aircraft reactions to obstacles, and assessing the navigation system quality.

The autonomous testing environment is a dense urban development with intervals between individual obstacles no more than 5 meters and a park area with open areas for testing UAV maneuvering and navigation among natural obstacles. At the same time, periodic interference of navigation signals can be caused by both "urban canyons" of signal loss and the presence of external intentional radio frequency interference.

The simulation results showed that the proposed Hardware-in-the-Loop simulation system of the UAV autonomous navigation ensures testing of group autonomous navigation models in difficult operating conditions, algorithms for restoring navigation parameters, optimal planning of the target flight path and real-time obstacle avoidance.

Drozd O.V. Hardware-in-the-loop simulation system of the unmanned aerial vehicle autonomous navigation. Achievements of modern radioelectronics. 2026. V. 80. No 3. P. 40–46. DOI: https://doi.org/10.18127/j20700784-202603-06 [in Russian]

1. Valavanis K. P., Vachtsevanos G. J. Handbook of unmanned aerial vehicles. Dordrecht: Springer. 2015. 3022 p. DOI: 10.1007/978-90-481-9707-1.
2. Budiyono A., Riyanto B., Joelianto E. Intelligent unmanned systems: theory and applications. Berlin, Heidelberg: Springer. 2009. 276 p. DOI: 10.1007/978-3-642-00264-9.
3. Liu J., Yue Z., Geng X., Wen S., Yan W. Long-life design and test technology of typical aircraft structures. Singapore: Springer. 2018. 154 p. DOI: 10.1007/978-981-10-8399-0.
4. Liu M., Egan G. K., Santoso F. Modeling, autopilot design, and field tuning of a UAV with minimum control surfaces. IEEE Transactions on Control Systems Technology. 2015. V. 23. №. 6. P. 2353-2360.
5. Drozd O., Avlasko P., Bordyugov S., Kapulin D. An automated measuring complex for research parameters of unmanned aerial vehicle. Smart Innovation, Systems and Technologies. 2021. V. 220. P. 419-430.
6. Sharma G., Jain S., Sharma R. S. Path planning for fully autonomous UAVs-A taxonomic review and future perspectives. IEEE Access. 2025. V. 13. P. 13356-13379. DOI: 10.1109/ACCESS.2025.35297547.
7. Tao H., Song T., Lin D., Jin R., Li B. Autonomous navigation and control system for capturing a moving drone. Field Robotics. 2022. V. 2. P. 34-54. DOI: 10.55417/fr.2022002.
8. Hashim H. A. Advances in UAV avionics systems architecture, classification and integration: a comprehensive review and future perspectives. Results in Engineering. 2025. V. 25. P. 103786. DOI: 10.1016/j.rineng.2024.103786.
9. Atyabi A., Zadeh S. M., Nefti-Meziani S. Current advancements on autonomous mission planning and management systems: An AUV and UAV perspective. Annual Reviews in Control. 2018. V. 46. P. 196-215. DOI: 10.1016/j.arcontrol.2018.07.002.
10. Bouabdallah S., Siegwart R. Full control of a quadrotor. IEEE/RSJ International Conference on Intelligent Robots and Systems. 2007. P. 153-158. DOI: 10.1109/IROS.2007.4399042.
11. Sai S., Garg A., Jhawar K., Chamola V., Sikdar B. A Comprehensive survey on artificial intelligence for unmanned aerial vehicles. IEEE Open Journal of Vehicular Technology. 2023. V. 4. P. 713-738. DOI: 10.1109/OJVT.2023.3316181.